© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 6-RES-JB
    11. 1094
    Prev
    Next
    INDEX
    Explanations

    information about animal behaviors and environmental habitats

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.6.hook_resid_post_16384_anthropic_fast_lr
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.25
    1.1%
    1842
    +0.14
    0.6%
    736
    +0.14
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    736
    +0.25
    0.12
    184
    +0.14
    -0.02
    394
    +0.14
    0.08
    Negative Logits
    <bos>
    -2.84
    <?
    -0.85
    ⓧ
    -0.83
    contentLoaded
    -0.81
    /***
    -0.80
    Autoritní
    -0.78
     anse
    -0.77
    /**
    -0.76
     Wicidata
    -0.76
    ///**
    -0.74
    POSITIVE LOGITS
     swarovski
    1.01
     ecru
    1.00
     tupperware
    0.96
     affor
    0.95
     impractica
    0.89
     embodi
    0.86
     pollut
    0.86
     bandeau
    0.86
     sulphuric
    0.86
     tricot
    0.85
    Activations Density 1.603%

    No Known Activations